Rail weld inspection methods, devices, electronic equipment and storage media
By acquiring vibration acceleration data collected from the vehicle-mounted axle box, and utilizing the track impact index and wavelet decomposition algorithm, we can accurately locate and assess weld defects in heavy-haul railway tracks, solving the problem of inaccurate detection and ensuring safe railway transportation.
Patent Information
- Application Number
- CN202411494728.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-24
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2044-10-24
AI Technical Summary
Existing technologies cannot accurately detect defects in welded seams of heavy-haul railway tracks, which affects the safety and stability of train operation and may even lead to safety accidents.
By acquiring vibration acceleration data collected from the vehicle axle box, the data is filtered using the wave-scraping algorithm of the track impact index, and combined with the feature defect separation algorithm of self-adjusting wavelet decomposition, the vibration data of weld feature defects are extracted and their energy values are calculated to determine the location and degree of weld defect.
It enables rapid and accurate detection of defects in rail welds, ensuring the safe transportation of heavy-haul railway tracks, and provides a reliable detection method and device.
Smart Images

Figure CN119459801B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of weld defect detection technology, and in particular to a method, apparatus, electronic device and storage medium for detecting rail weld defects. Background Technology
[0002] With the continuous increase in annual freight volume and operating mileage of heavy-haul railways, problems arising from wheel-rail contact are emerging one after another. These include damage to mobile equipment and infrastructure components caused by wheel-rail impact, disturbance to residents along the line due to wheel-rail noise, and increased maintenance costs. Unevenness in rail welded joints is a major and prominent defect, causing a series of significant wheel-rail dynamic interaction problems, worsening the condition of heavy-haul railway lines, and consequently affecting the safety and stability of heavy-haul train operation. In severe cases, it may even lead to serious safety accidents such as derailment and overturning of heavy-haul trains.
[0003] Currently, heavy-haul railway comprehensive inspection vehicles are mainly used to inspect the track conditions of heavy-haul railways. The inspection trains are equipped with equipment for detecting track geometry and vehicle dynamic response. The vehicle dynamic response includes axle box acceleration sensors, which can collect the acceleration of the axle boxes in the lateral and vertical directions in real time. However, the operating speed and axle load of the inspection trains are quite different from those of actual operating vehicles, making it impossible to accurately detect the track conditions.
[0004] Therefore, researching a weld defect detection method based on the track impact index to quickly and accurately detect track welds using vibration acceleration data is of great significance for identifying the distribution of track weld defects, ensuring that heavy-haul railway tracks are in safe use, and promoting the sustainable development of railway rail transportation. Summary of the Invention
[0005] This invention provides a method, apparatus, electronic device, and storage medium for detecting track welds, which solves the problem of inaccurate track weld detection results and lays an important foundation for the safe transportation of heavy-haul railway tracks.
[0006] In a first aspect, the present invention provides a method for inspecting rail welds, comprising:
[0007] Acquire vibration acceleration data of the track under test from the vehicle-mounted axle box;
[0008] The vibration acceleration data is filtered using a wave-scraping filtering algorithm based on the track impact index to obtain track impact index data.
[0009] The weld defect data in the track impact index data is detected to determine the location of the weld defect in the track under test.
[0010] The vibration data of weld feature defects are extracted from the vibration acceleration data corresponding to the location of the weld defect by using the feature defect separation algorithm of self-adjusting wavelet decomposition.
[0011] The energy value of the vibration data of the weld defect characteristics is calculated to determine the degree of weld defect deterioration of the track under test.
[0012] Optionally, a wave-scraping filtering algorithm based on the track impact index is used to filter the vibration acceleration data to obtain track impact index data, including:
[0013] According to the preset formula for calculating the effective value of movement, the vibration acceleration data is normalized to obtain the preliminary track impact index.
[0014] Using a preset threshold segmentation as the length unit, corrugated segments in the preliminary track impact index with abnormal data lengths greater than the preset corrugation threshold are removed to obtain the track impact index data; the abnormal data refers to data in the preliminary track impact index that is greater than the preset corrugation threshold; the abnormal data length is the length of consecutively occurring abnormal data when the abnormal data appears in the preliminary track impact index.
[0015] Optionally, the vibration acceleration data is normalized according to a preset formula for calculating the effective value of movement to obtain a preliminary track impact index, including:
[0016] Based on the preset formula for calculating effective values of movement, multiple effective values of movement in the vibration acceleration data are calculated.
[0017] The preliminary orbital impact index is obtained based on the ratio of multiple moving effective values to the average of multiple moving effective values.
[0018] Optionally, using a preset threshold segmentation as the length unit, corrugated segments with abnormal data lengths greater than the preset threshold segmentation are removed from the preliminary track impact index to obtain the track impact index data, including:
[0019] Using the preset threshold segmentation as the length unit, the data length of the abnormal data in the preliminary orbital impact index is detected to determine whether the data length of each abnormal data in the preliminary orbital impact index is greater than the length unit.
[0020] If so, then abnormal data with a length greater than the length unit are identified as corrugated sections, and the corrugated sections are removed from the preliminary track impact index to obtain the track impact index data;
[0021] If not, then the abnormal data in the preliminary track impact index is determined to be a non-erosion section, and the track impact index data is obtained.
[0022] Optionally, detecting weld defect data in the track impact index data to determine the location of weld defects in the track under test includes:
[0023] Based on the preset formula for calculating the threshold of irregularity defects, the preliminary weld defect data in the track impact index data is calculated.
[0024] The weld defect data is obtained by selecting data whose corresponding effective value of movement is greater than the preset 3σ extraction threshold from the preliminary weld defect data;
[0025] The location of the weld defect is determined by the track position on the track to be tested, based on the weld defect data.
[0026] Optionally, the characteristic defect vibration data of the weld is extracted from the vibration acceleration data corresponding to the location of the weld defect using a self-adjusting wavelet decomposition characteristic defect separation algorithm, including:
[0027] Extract the vibration acceleration data corresponding to the location of the weld defect and record it as weld vibration acceleration data;
[0028] According to the preset wavelet basis function, the weld vibration acceleration data is converted into corresponding wavelet coefficients, and the wavelet coefficients greater than the preset wavelet threshold are extracted as data containing only the fault feature components to obtain effective fault signal data.
[0029] Non-zero wavelet coefficients are extracted from the effective fault signal data to obtain the vibration data of weld characteristic defects.
[0030] In a second aspect, the present invention provides a track weld inspection device, comprising:
[0031] The acquisition module is used to acquire vibration acceleration data of the track under test collected by the vehicle-mounted axle box.
[0032] The filtering module is used to filter the vibration acceleration data based on the erosion filtering algorithm of the track impact index to obtain the track impact index data.
[0033] The detection module is used to detect weld defect data in the track impact index data to determine the location of weld defects in the track under test.
[0034] The extraction module is used to extract the vibration data of the weld feature defects from the vibration acceleration data corresponding to the location of the weld defect by using a feature defect separation algorithm based on self-adjusting wavelet decomposition.
[0035] The calculation module is used to calculate the energy value of the vibration data of the weld feature defects in order to determine the degree of weld defect deterioration information of the track under test.
[0036] Thirdly, the present invention provides an electronic device including a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the steps of the method provided in the first aspect above.
[0037] Fourthly, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the method provided in the first aspect above.
[0038] Fifthly, the present invention provides a computer program product comprising a computer program / instructions, wherein when the computer program is executed by a processor, it performs the steps of the method provided in the first aspect above.
[0039] As can be seen from the above technical solutions, the present invention has the following advantages:
[0040] This invention provides a method, apparatus, electronic device, and storage medium for detecting rail welds. The method includes: acquiring vibration acceleration data of the track under test collected by an on-board axle box; filtering the vibration acceleration data based on a wave-scraping filtering algorithm using the track impact index to obtain track impact index data; detecting weld defect data in the track impact index data to determine the location of weld defects in the track under test; extracting characteristic weld defect vibration data from the vibration acceleration data corresponding to the weld defect location using a self-adjusting wavelet decomposition characteristic defect separation algorithm; calculating the energy value of the characteristic weld defect vibration data to determine the degree of weld defect deterioration information of the track under test and calculating the corresponding target section of the track weld detection value. This establishes a method for detecting rail weld defects using vibration acceleration data, solving the problem of inaccurate rail weld detection results and laying an important foundation for the safe transportation of heavy-haul railway tracks. Attached Figure Description
[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0042] Figure 1 This is a flowchart illustrating the steps of a first embodiment of the rail weld inspection method of the present invention;
[0043] Figure 2 This is a flowchart illustrating the steps of a second embodiment of the rail weld inspection method of the present invention.
[0044] Figure 3 This is a schematic diagram of vibration acceleration data and track impact index data according to the present invention;
[0045] Figure 4 This is a schematic diagram of an orbital impact index data according to the present invention;
[0046] Figure 5 This is a schematic diagram of weld defect data according to the present invention;
[0047] Figure 6 This is a schematic diagram of wavelet coefficients according to the present invention;
[0048] Figure 7 This is a structural block diagram of an embodiment of a track weld inspection device according to the present invention. Detailed Implementation
[0049] This invention provides a method, apparatus, electronic device, and storage medium for detecting track welds, which solves the problem of difficult detection of track welds in abnormally high-pressure sections and lays an important foundation for the safe transportation of heavy-haul railway tracks.
[0050] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0051] Example 1
[0052] Please see Figure 1 , Figure 1 This is a flowchart illustrating the steps of a method for inspecting rail welds according to an embodiment of the present invention. The method includes:
[0053] Step S101: Obtain the vibration acceleration data of the track under test collected by the vehicle axle box;
[0054] This invention provides an embodiment of the method for acquiring vibration acceleration data about the track under test collected by an acceleration sensor on the axle box of a test train.
[0055] Step S102: Based on the wave-scraping filtering algorithm of the track impact index, the vibration acceleration data is filtered to obtain the track impact index data;
[0056] In one optional embodiment, a wave-slip filtering algorithm based on the track impact index is used to filter the vibration acceleration data to obtain track impact index data, including:
[0057] According to the preset formula for calculating the effective value of movement, the vibration acceleration data is normalized to obtain the preliminary track impact index.
[0058] Using a preset threshold segmentation as the length unit, corrugated segments in the preliminary track impact index with abnormal data lengths greater than the preset corrugation threshold are removed to obtain the track impact index data; the abnormal data refers to data in the preliminary track impact index that is greater than the preset corrugation threshold; the abnormal data length is the length of consecutively occurring abnormal data when the abnormal data appears in the preliminary track impact index.
[0059] According to a preset formula for calculating the effective value of movement, the effective value of movement in the vibration acceleration data is calculated. Based on the ratio of the effective value of movement to the average value of the effective value of movement, a preliminary track impact index is obtained. Using a preset threshold segmentation as the length unit, the data length of abnormal data in the preliminary track impact index is detected to determine whether the data length of each abnormal data in the preliminary track impact index is greater than the length unit. If so, the abnormal data with a data length greater than the length unit is determined to be a corrugated segment, and the corrugated segment is removed from the preliminary track impact index to obtain the track impact index data. If not, it indicates that the abnormal data in the preliminary track impact index is a non-corrugated segment, and the track impact index data is obtained.
[0060] Step S103: Detect weld defect data in the track impact index data to determine the location of weld defects in the track to be tested;
[0061] This invention uses a differential positioning algorithm based on the 3σ criterion to obtain weld defect data from track impact index data. According to a preset irregularity defect threshold calculation formula, preliminary weld defect data from track impact index data is calculated. Data with corresponding effective values greater than the preset 3σ extraction threshold are extracted from the preliminary weld defect data to obtain weld defect data. The track position of the weld defect data on the track to be tested is determined as the weld defect location.
[0062] Step S104: Using the feature defect separation algorithm of self-adjusting wavelet decomposition, the vibration data of the weld feature defect is extracted from the vibration acceleration data corresponding to the location of the weld defect.
[0063] In this embodiment of the invention, vibration acceleration data corresponding to the location of weld defects is extracted and denoted as weld vibration acceleration data. According to a preset wavelet basis function, the weld vibration acceleration data is converted into corresponding wavelet coefficients. Based on a preset wavelet threshold, data containing only defect feature components is extracted from the wavelet coefficients to obtain effective fault signal data. Non-zero wavelet coefficients are extracted from the effective fault signal data to obtain weld feature defect vibration data.
[0064] Step S105: Calculate the energy value of the vibration data of the weld feature defects in order to detect the degree of weld defect deterioration of the track under test.
[0065] In this embodiment of the invention, the energy value of the vibration data of weld feature defects is calculated by a preset energy value calculation formula. The degree of weld defect deterioration of the track under test is determined by the magnitude of the energy value. The larger the energy value, the more severe the defect deterioration.
[0066] This invention provides a method for detecting rail welds, comprising: acquiring vibration acceleration data of the track under test collected by an on-board axle box; filtering the vibration acceleration data based on a wave-scraping filtering algorithm using the track impact index to obtain track impact index data; detecting weld defect data in the track impact index data to determine the location of weld defects in the track under test; extracting characteristic weld defect vibration data from the vibration acceleration data corresponding to the weld defect location using a self-adjusting wavelet decomposition characteristic defect separation algorithm; calculating the energy value of the characteristic weld defect vibration data to determine the degree of weld defect deterioration information of the track under test and calculating the corresponding target section of the track weld detection value. This establishes a method for detecting rail weld defects using vibration acceleration data, solving the problem of inaccurate rail weld detection results and laying an important foundation for the safe transportation of heavy-haul railway tracks.
[0067] Example 2
[0068] Please see Figure 2 , Figure 2 This is a flowchart illustrating a second embodiment of the rail weld inspection method of the present invention. The steps include:
[0069] S201, acquire vibration acceleration data of the track under test collected by the vehicle axle box;
[0070] This invention obtains vibration acceleration data about the track under test from the acceleration sensor in the axle box of the detection train.
[0071] S202, According to the preset formula for calculating the effective value of movement, the vibration acceleration data is normalized to obtain the preliminary track impact index;
[0072] In an optional embodiment, the vibration acceleration data is normalized according to a preset formula for calculating the effective value of movement to obtain a preliminary track impact index, including:
[0073] Based on the preset formula for calculating effective values of movement, multiple effective values of movement in the vibration acceleration data are calculated.
[0074] The preliminary orbital impact index is obtained based on the ratio of multiple moving effective values to the average of multiple moving effective values.
[0075] In this embodiment of the invention, multiple moving effective values are calculated using the formula for calculating moving effective values. Each moving effective value is then compared with the average of the multiple moving effective values to obtain a preliminary orbital impact index.
[0076] The preset formula for calculating the effective value of movement is as follows:
[0077]
[0078] Among them, S r Here, N is the effective value of the vibration acceleration at the measuring point, K is the total length of the track position, and x is the preset movement window length. i This represents the vibration acceleration data at the i-th orbital position.
[0079] S203, using a preset threshold segmentation as the length unit, remove corrugated segments in the preliminary track impact index whose abnormal data length is greater than the preset corrugation threshold to obtain the track impact index data; the abnormal data is the data in the preliminary track impact index that is greater than the preset corrugation threshold; the abnormal data length is the data length of the abnormal data that appears consecutively when the abnormal data appears in the preliminary track impact index.
[0080] In an optional embodiment, using a preset threshold segmentation as the length unit, corrugated segments with abnormal data lengths greater than the preset threshold segmentation are removed from the preliminary track impact index to obtain the track impact index data, including:
[0081] Using the preset threshold segmentation as the length unit, the data length of the abnormal data in the preliminary orbital impact index is detected to determine whether the data length of each abnormal data in the preliminary orbital impact index is greater than the length unit.
[0082] If so, then abnormal data with a length greater than the length unit are identified as corrugated sections, and the corrugated sections are removed from the preliminary track impact index to obtain the track impact index data;
[0083] If not, then the abnormal data in the preliminary track impact index is determined to be a non-erosion section, and the track impact index data is obtained.
[0084] In this embodiment of the invention, corrugation defects need to be prioritized for removal. Since multiple defects often occur in the track, corrugation defects frequently appear near track welding irregularities. Corrugation defects affect the inspection results of rail welding. Therefore, data containing corrugation defects needs to be removed from the data. Data containing corrugation defects and data containing track welding irregularities have different characteristics. Data containing corrugation defects is continuous and is generally referred to as corrugated sections. Therefore, using a preset threshold to divide the sections as length units, abnormal data in the preliminary track impact index with a length greater than the length unit are identified as corrugated sections. Corrugated sections are removed from the preliminary track impact index to obtain the track impact index data. If there is no data with a length greater than the length unit in the preliminary track impact index, then no data removal is necessary, and the preliminary track impact index is determined as the track impact index data.
[0085] For example, take a segment of simulated vibration acceleration data, which includes a segment of corrugation defect (10m long, 180mm wavelength, 0.1mm depth) and two segments of weld joint irregularities (100mm wavelength, ±0.5mm depth respectively). Calculate the track impact index for this segment of data, such as... Figure 3 As shown, Figure 3 Curve 'a' at the top represents the original vibration acceleration data, and curve 'b' at the bottom represents the track impact index data. The horizontal axis represents the track position in meters, and the vertical axis represents the acceleration in m / s². 2 .from Figure 3 It can be seen that data containing corrugation defects exhibits a continuous high index phenomenon, with the duration being the same as the length of the corrugation defect itself. Weld defects, on the other hand, only cause localized impact phenomena. Therefore, a segmentation technique based on continuously exceeding a preset corrugation threshold is used to filter out corrugation defects. When corrugation defects occur in the track, the calculated track impact index will show intervals continuously exceeding the preset corrugation threshold. Conversely, when weld irregularities occur, data points locally exceeding the preset corrugation threshold will appear, such as... Figure 4 As shown, Figure 4 The marked interval 'c' represents the corrugated section, where the horizontal axis represents the track position in meters, and the vertical axis represents the acceleration in m / s². 2 At this point, the corrugated section is removed to eliminate the impact of corrugation defects.
[0086] S204, according to the preset irregularity defect threshold calculation formula, the preliminary weld defect data in the track impact index data is calculated;
[0087] In this embodiment of the invention, after acquiring the track impact index data, weld defect data within the track impact index data is obtained through a difference localization algorithm based on the 3σ criterion. Preliminary weld defect data is calculated based on a preset irregularity defect threshold calculation formula. The difference localization algorithm based on the 3σ criterion is a method for finding anomalies in the track impact index using the median 3σ criterion. It locates the abnormal positions in the track impact index through multiple outlier removal processes. First, assuming the data contains only random errors, the standard deviation is calculated, and an interval is determined. This interval contains random errors with a certain probability; errors exceeding this interval are considered gross errors and should be removed. According to the 3σ criterion, the probability of values distributed within (μ-3σ, μ+3σ) is 0.9974, meaning most normal data falls within this interval. When weld irregularities occur in the track, they cause localized impacts. Calculating the track impact index for these impacts will result in range-bound outliers. These outliers can be considered gross errors and removed using the 3σ criterion.
[0088] The preset formula for calculating the threshold of unevenness defects is as follows:
[0089] T d = x_median + 3σ;
[0090] Among them, T d The threshold value for unevenness defects is given by x_median, where x is the median vibration acceleration and σ is the variance.
[0091] When x i Greater than T d At that time, the orbital impact index TII was set. i =x_median, which means that the data on weld defects has been removed.
[0092] S205, Select data from the preliminary weld defect data whose corresponding effective value of movement is greater than the preset 3σ extraction threshold to obtain the weld defect data;
[0093] In this embodiment of the invention, since these weld defect data are range-bound anomalies and cannot be accurately eliminated in one go, the data after elimination is further processed using the 3σ criterion for error elimination (i.e., the above steps are repeated) until no gross errors exist. Specifically, before eliminating these weld defect data, these weld defect data are first marked, and the location of welding irregularities is determined based on the marked weld defect data, thus obtaining the location of the weld defect.
[0094] S206, The position of the weld defect data on the track to be tested is determined as the location of the weld defect;
[0095] By performing difference analysis on the processed data and the original data, the location of track welding irregularities can be preliminarily determined. To further confirm the accuracy of the identified anomaly locations, the track impact index is checked, and only anomaly areas with track impact index values greater than a certain value are retained. This process ultimately allows for the location of the welding irregularities.
[0096] like Figure 5 As shown, box d represents the marked weld defect data, indicating the location of the weld defect. The horizontal axis represents the track position in meters, and the vertical axis represents the acceleration in m / s². 2 .
[0097] S207, Extract the vibration acceleration data corresponding to the location of the weld defect and record it as weld vibration acceleration data;
[0098] It should be noted that wavelet transform (WT) is a signal processing technique based on multi-scale analysis, used to analyze the frequency components and time-domain characteristics of signals or data, and has wide applications in signal and image processing. During wavelet transform processing, different features of the signal can be obtained by selecting different types of wavelet functions. Wavelet transform can decompose a signal into signal components at different scales and selectively recombine them based on the scale differences between noise and the signal. In the field of wavelet signal processing, wavelet denoising algorithms based on soft thresholding and hard thresholding are among the most widely used methods.
[0099] In this embodiment of the invention, the original vibration acceleration data corresponding to the location of the weld defect after positioning is obtained, and the weld vibration acceleration data is obtained. The weld vibration acceleration data contains a high content of weld defect data, but there is still interference from track irregularities and other signals. Therefore, self-adjusting wavelet decomposition is proposed to analyze the weld vibration acceleration data, thereby realizing the separation of defect characteristic components.
[0100] S208, according to the preset wavelet basis function, the weld vibration acceleration data is converted into corresponding wavelet coefficients, and the wavelet coefficients greater than the preset wavelet threshold are extracted as data containing only the fault feature components to obtain effective fault signal data;
[0101] According to the preset wavelet basis function, the weld vibration acceleration data is converted into corresponding wavelet coefficients. Since the frequency distribution of the characteristic vibration signal caused by the weld joint is around a center frequency band, the self-adjusting wavelet decomposition uses hard thresholding to extract the wavelet coefficients around this center frequency band, that is, retaining the wavelet coefficients of the center frequency band and setting other coefficients to zero, thereby forming the target decoupling filter W. Finally, the defect characteristic signal is obtained by reconstructing the wavelet coefficients. The specific algorithm steps are as follows:
[0102] (1) Select a suitable wavelet basis function u (i.e., the preset wavelet basis function), decompose the weld vibration acceleration data using the corresponding decomposition scale j and perform discrete wavelet transform to obtain the wavelet coefficients at each scale.
[0103] (2) Set the wavelet threshold Th, perform threshold processing on each wavelet coefficient to retain wavelet coefficients greater than the wavelet threshold Th, and then reconstruct the other wavelet coefficients (i.e. set the other wavelet coefficients to zero) to obtain a preliminary effective fault signal.
[0104] (3) Modify the wavelet threshold Th and repeat (2) until the data in the initial effective fault signal contains only the fault feature components, and the data is the effective fault signal data.
[0105] S209, extract non-zero wavelet coefficients from the effective fault signal data to obtain the vibration data of weld characteristic defects.
[0106] In this embodiment of the invention, the wavelet coefficients of the effective fault signal data are obtained in the region where the wavelet coefficients are not zero. The wavelet coefficients of this region are recorded, and the desired decoupling filter W is constructed to reconstruct the fault and obtain the vibration data of the weld characteristic fault.
[0107] like Figure 6 As shown, curve f represents vibration acceleration data, and curve g represents vibration data of weld characteristic defects. The weld vibration acceleration data is analyzed using a preset wavelet basis function to obtain the weld characteristic defect vibration data for curve g. The horizontal axis represents the track position in meters, and the vertical axis represents the acceleration in m / s². 2 .
[0108] S2010, calculate the energy value of the vibration data of the weld feature defects to determine the degree of weld defect deterioration of the track under test.
[0109] According to the preset energy value calculation formula, the energy value of the vibration data of the characteristic defects of the weld is calculated, and the degree of weld defect deterioration of the track under test is determined according to the magnitude of the energy value, so as to obtain the information on the degree of weld defect deterioration of the track under test. The larger the energy value, the more serious the defect deterioration, and the smaller the energy value, the less serious the defect deterioration.
[0110] The preset energy value calculation formula is as follows:
[0111]
[0112] Where E is the energy value.
[0113] This invention discloses a method for detecting rail welds, comprising: acquiring vibration acceleration data of the track under test collected by an on-board axle box; filtering the vibration acceleration data based on a wave-scraping filtering algorithm using the track impact index to obtain track impact index data; detecting weld defect data in the track impact index data to determine the location of weld defects in the track under test; extracting characteristic defect vibration data of the weld from the vibration acceleration data corresponding to the location of the weld defect using a self-adjusting wavelet decomposition characteristic defect separation algorithm; and calculating the energy value of the characteristic defect vibration data of the weld to determine the degree of weld defect deterioration information of the track under test. This method solves the problem of inaccurate rail weld detection results, laying an important foundation for the safe transportation of heavy-haul railway tracks. Furthermore, this method is highly operable, providing a clear and intuitive understanding of the rail weld detection process in practical use, and can be easily applied to the detection of defects in heavy-haul railway tracks.
[0114] Example 3
[0115] Please see Figure 7 , Figure 7 This is a structural block diagram of an embodiment of a track weld inspection device according to the present invention. The device includes:
[0116] The acquisition module 301 is used to acquire the vibration acceleration data of the track under test collected by the vehicle axle box;
[0117] The filtering module 302 is used to filter the vibration acceleration data based on the wave-scraping filtering algorithm of the track impact index to obtain the track impact index data.
[0118] The detection module 303 is used to detect weld defect data in the track impact index data to determine the location of weld defects in the track to be tested.
[0119] Extraction module 304 is used to extract weld feature defect vibration data from the vibration acceleration data corresponding to the weld defect location using a feature defect separation algorithm based on self-adjusting wavelet decomposition.
[0120] The calculation module 305 is used to calculate the energy value of the vibration data of the weld feature defects in order to determine the degree of weld defect deterioration information of the track under test.
[0121] In an optional embodiment, the filtering module 302 includes:
[0122] The normalization processing submodule is used to normalize the vibration acceleration data according to the preset effective value calculation formula to obtain the preliminary track impact index.
[0123] The elimination submodule is used to eliminate corrugated segments in the preliminary track impact index whose abnormal data length is greater than the preset threshold segment length unit, thereby obtaining the track impact index data; the abnormal data is the data in the preliminary track impact index that is greater than the preset corrugation threshold; the abnormal data length is the data length of the abnormal data that appears consecutively when the abnormal data appears in the preliminary track impact index.
[0124] In an optional embodiment, the normalization processing submodule includes:
[0125] The calculation unit is used to calculate multiple effective values of movement in the vibration acceleration data according to the preset effective value of movement calculation formula;
[0126] The ratio unit is used to obtain the preliminary orbital impact index based on the ratio of a plurality of said moving effective values to the average of the plurality of said moving effective values.
[0127] In an optional embodiment, the rejection submodule includes:
[0128] The judgment unit is used to detect the data length of the abnormal data in the preliminary orbital impact index using the preset threshold segmentation as the length unit, so as to determine whether the data length of each abnormal data in the preliminary orbital impact index is greater than the length unit; if yes, then the elimination unit is executed; if no, then the determination unit is executed.
[0129] The elimination unit is used to determine abnormal data whose data length is greater than the length unit as a corrugated section, and to eliminate the corrugated section from the preliminary track impact index to obtain the track impact index data;
[0130] The determining unit is used to determine that the abnormal data in the preliminary track impact index is a non-erosion section, and to obtain the track impact index data.
[0131] In an optional embodiment, the detection module 303 includes:
[0132] The calculation submodule is used to calculate the preliminary weld defect data in the track impact index data according to the preset irregularity defect threshold calculation formula.
[0133] The selection module is used to select data from the preliminary weld defect data whose corresponding effective value of movement is greater than the preset 3σ extraction threshold, so as to obtain the weld defect data.
[0134] The determination submodule is used to determine the location of the weld defect as the location of the weld defect on the track to be tested.
[0135] In an optional embodiment, the extraction module 304 includes:
[0136] The first extraction submodule is used to extract the vibration acceleration data corresponding to the location of the weld defect, and denoted as weld vibration acceleration data;
[0137] The second extraction submodule is used to convert the weld vibration acceleration data into corresponding wavelet coefficients according to the preset wavelet basis function, and extract the wavelet coefficients that are greater than the preset wavelet threshold as data containing only the fault feature components to obtain effective fault signal data.
[0138] The third extraction submodule is used to extract non-zero wavelet coefficients from the effective fault signal data to obtain vibration data of weld characteristic defects.
[0139] Example 4
[0140] This invention also provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a rail weld inspection method according to any embodiment.
[0141] Example 5
[0142] This invention also provides a computer storage medium storing a computer program thereon, which, when executed by the processor, implements the steps of a rail weld inspection method according to any embodiment.
[0143] Example 6
[0144] This invention also provides a computer program product having a computer program stored thereon, wherein the computer program, when executed by the processor, implements the steps of a track weld inspection method according to any embodiment.
[0145] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0146] In the several embodiments provided in this application, it should be understood that the methods, apparatuses, electronic devices, and storage media disclosed in this invention can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0147] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0148] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0149] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0150] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for inspecting rail welds, characterized in that, include: Acquire vibration acceleration data of the track under test from the vehicle-mounted axle box; The erosion filtering algorithm based on the track impact index is used to filter the vibration acceleration data to obtain the track impact index data. The weld defect data in the track impact index data is detected to determine the location of the weld defect in the track under test. The vibration data of weld feature defects are extracted from the vibration acceleration data corresponding to the location of the weld defect by using the feature defect separation algorithm of self-adjusting wavelet decomposition. The energy value of the vibration data of the weld defect characteristics is calculated to determine the degree of weld defect deterioration of the track under test; The erosion filtering algorithm based on the track impact index filters the vibration acceleration data to obtain track impact index data, including: According to the preset formula for calculating the effective value of movement, the vibration acceleration data is normalized to obtain the preliminary track impact index. Using a preset threshold segmentation as the length unit, corrugated segments in the preliminary track impact index with abnormal data lengths greater than the preset corrugation threshold are removed to obtain the track impact index data; the abnormal data refers to data in the preliminary track impact index that is greater than the preset corrugation threshold; the abnormal data length is the length of consecutively occurring abnormal data when the abnormal data appears in the preliminary track impact index.
2. The method for inspecting track welds according to claim 1, characterized in that, Based on a preset formula for calculating the effective value of movement, the vibration acceleration data is normalized to obtain a preliminary track impact index, including: Based on the preset formula for calculating effective values of movement, multiple effective values of movement in the vibration acceleration data are calculated. The preliminary orbital impact index is obtained based on the ratio of multiple moving effective values to the average of multiple moving effective values.
3. The method for inspecting rail welds according to claim 1, characterized in that, Using a preset threshold segmentation as the length unit, the erosion segments with abnormal data lengths exceeding the preset threshold in the preliminary track impact index are removed to obtain the track impact index data, including: Using the preset threshold segmentation as the length unit, the data length of the abnormal data in the preliminary orbital impact index is detected to determine whether the data length of each abnormal data in the preliminary orbital impact index is greater than the length unit. If so, then abnormal data with a length greater than the length unit are identified as corrugated sections, and the corrugated sections are removed from the preliminary track impact index to obtain the track impact index data; If not, then the abnormal data in the preliminary track impact index is determined to be a non-erosion section, and the track impact index data is obtained.
4. The method for inspecting track welds according to claim 1, characterized in that, Detecting weld defect data in the track impact index data to determine the location of weld defects in the track under test includes: Based on the preset formula for calculating the threshold of irregularity defects, the preliminary weld defect data in the track impact index data is calculated. The weld defect data is obtained by selecting data whose corresponding effective value of movement is greater than the preset 3σ extraction threshold from the preliminary weld defect data; The location of the weld defect is determined by the track position on the track to be tested, based on the weld defect data.
5. The method for inspecting rail welds according to claim 1, characterized in that, The feature defect separation algorithm of self-adjusting wavelet decomposition is used to extract the vibration data of the weld feature defects from the vibration acceleration data corresponding to the location of the weld defect, including: Extract the vibration acceleration data corresponding to the location of the weld defect and record it as weld vibration acceleration data; According to the preset wavelet basis function, the weld vibration acceleration data is converted into corresponding wavelet coefficients, and the wavelet coefficients greater than the preset wavelet threshold are extracted as data containing only the fault feature components to obtain effective fault signal data. Non-zero wavelet coefficients are extracted from the effective fault signal data to obtain the vibration data of weld characteristic defects.
6. A track weld inspection device, characterized in that, include: The acquisition module is used to acquire vibration acceleration data of the track under test collected by the vehicle-mounted axle box. The filtering module is used to filter the vibration acceleration data based on the erosion filtering algorithm of the track impact index to obtain the track impact index data. The detection module is used to detect weld defect data in the track impact index data to determine the location of weld defects in the track under test. The extraction module is used to extract the vibration data of the weld feature defects from the vibration acceleration data corresponding to the location of the weld defect by means of a feature defect separation algorithm based on self-adjusting wavelet decomposition. The calculation module is used to calculate the energy value of the vibration data of the weld feature defects in order to determine the degree of weld defect deterioration information of the track under test; The filtering module includes: The normalization processing submodule is used to normalize the vibration acceleration data according to the preset effective value calculation formula to obtain the preliminary track impact index. The elimination submodule is used to eliminate corrugated segments in the preliminary track impact index whose abnormal data length is greater than the preset threshold segment length unit, thereby obtaining the track impact index data; the abnormal data is the data in the preliminary track impact index that is greater than the preset corrugation threshold; the abnormal data length is the data length of the abnormal data that appears consecutively when the abnormal data appears in the preliminary track impact index.
7. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the method as described in any one of claims 1-5.
8. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it performs the method as described in any one of claims 1-5.
9. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1-5.
Citation Information
Patent Citations
Steel rail short wave disease type identification method and device, and electronic equipment
CN113281414A
